Update README.md

README.md

@@ -4,6 +4,8 @@ baichuan-vicuna-7b is a chat model supervised finetuned on vicuna sharegpt data.
 - The finetuning data includes [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split.json), mixed with [COT](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT) and [Leetcode](https://www.kaggle.com/datasets/erichartford/leetcode-solutions), which are aimed to improve the model's reasoning and coding ability (the data mixing strategy is inspired by [TULU](https://arxiv.org/abs/2306.04751)).
 - The training code is based on [FastChat](https://github.com/lm-sys/FastChat), with the prompt format consisting of [Vicuna v1.1](https://huggingface.co/lmsys/vicuna-7b-delta-v1.1).
 
+[中文说明](#chinese-model-card)
+
 # Inference with FastChat
 ```
 python3 -m fastchat.serve.cli --model-path fireballoon/baichuan-vicuna-7b
@@ -76,7 +78,7 @@ This algorithm has a runtime complexity of O(log n) and a space complexity of O(
 
 ---
 
-# baichuan-vicuna-7b
+# Chinese model card
 
 baichuan-vicuna-7b是在vicuna sharegpt数据上全参数微调的对话模型。
 - 基座模型是[baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B)，由百川智能开发的可商用大规模预训练模型。